Thermal Preference

Thermal preference research focuses on understanding and predicting individual comfort levels in response to temperature and humidity, aiming to optimize building climate control and energy efficiency. Current research employs machine learning models, including large language models (LLMs), reinforcement learning algorithms, and graph neural networks, to personalize thermal comfort predictions based on individual characteristics, activity, and environmental data. These efforts leverage active learning techniques to minimize data collection burden while improving model accuracy, leading to more efficient and personalized HVAC systems and potentially enhancing occupant well-being in buildings and other environments.

Papers